You can deploy this model and start earning money today!

RichardErkhov/
tsavage68_-_IE_L3_350steps_1e8rate_03beta_cSFTDPO-gguf

Name: tsavage68_-_IE_L3_350steps_1e8rate_03beta_cSFTDPO-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

IE_L3_350steps_1e8rate_03beta_cSFTDPO - GGUF

Model creator: https://huggingface.co/tsavage68/
Original model: https://huggingface.co/tsavage68/IE_L3_350steps_1e8rate_03beta_cSFTDPO/

Name	Quant method	Size
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q2_K.gguf	Q2_K	2.96GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.IQ3_XS.gguf	IQ3_XS	3.28GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.IQ3_S.gguf	IQ3_S	3.43GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q3_K_S.gguf	Q3_K_S	3.41GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.IQ3_M.gguf	IQ3_M	3.52GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q3_K.gguf	Q3_K	3.74GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q3_K_M.gguf	Q3_K_M	3.74GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q3_K_L.gguf	Q3_K_L	4.03GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.IQ4_XS.gguf	IQ4_XS	4.18GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q4_0.gguf	Q4_0	4.34GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.IQ4_NL.gguf	IQ4_NL	4.38GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q4_K_S.gguf	Q4_K_S	4.37GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q4_K.gguf	Q4_K	4.58GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q4_K_M.gguf	Q4_K_M	4.58GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q4_1.gguf	Q4_1	4.78GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q5_0.gguf	Q5_0	5.21GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q5_K_S.gguf	Q5_K_S	5.21GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q5_K.gguf	Q5_K	5.34GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q5_K_M.gguf	Q5_K_M	5.34GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q5_1.gguf	Q5_1	5.65GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q6_K.gguf	Q6_K	6.14GB
IE_L3_350steps_1e8rate_03beta_cSFTDPO.Q8_0.gguf	Q8_0	7.95GB

Original model description:

library_name: transformers license: llama3 base_model: tsavage68/IE_L3_1000steps_1e6rate_SFT tags:

trl
dpo
generated_from_trainer model-index:
name: IE_L3_350steps_1e8rate_03beta_cSFTDPO results: []

IE_L3_350steps_1e8rate_03beta_cSFTDPO

This model is a fine-tuned version of tsavage68/IE_L3_1000steps_1e6rate_SFT on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6896
Rewards/chosen: -0.0071
Rewards/rejected: -0.0198
Rewards/accuracies: 0.4400
Rewards/margins: 0.0127
Logps/rejected: -75.6932
Logps/chosen: -82.8214
Logits/rejected: -0.7977
Logits/chosen: -0.7408

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-08
train_batch_size: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 350

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.6912	0.4	50	0.6940	-0.0075	-0.0104	0.4000	0.0029	-75.6618	-82.8226	-0.7964	-0.7393
0.6947	0.8	100	0.6925	0.0014	-0.0057	0.3850	0.0070	-75.6461	-82.7931	-0.7963	-0.7394
0.6881	1.2	150	0.7003	-0.0102	-0.0020	0.375	-0.0082	-75.6340	-82.8318	-0.7969	-0.7398
0.6776	1.6	200	0.6938	-0.0057	-0.0098	0.375	0.0041	-75.6601	-82.8168	-0.7970	-0.7399
0.6859	2.0	250	0.6850	-0.0033	-0.0250	0.4350	0.0217	-75.7105	-82.8087	-0.7975	-0.7405
0.7024	2.4	300	0.6893	-0.0075	-0.0207	0.4400	0.0132	-75.6964	-82.8228	-0.7977	-0.7408
0.6802	2.8	350	0.6896	-0.0071	-0.0198	0.4400	0.0127	-75.6932	-82.8214	-0.7977	-0.7408

Framework versions

Transformers 4.44.2
Pytorch 2.0.0+cu117
Datasets 3.0.0
Tokenizers 0.19.1

RichardErkhov/tsavage68_-_IE_L3_350steps_1e8rate_03beta_cSFTDPO-gguf

Original model description:

IE_L3_350steps_1e8rate_03beta_cSFTDPO

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
tsavage68_-_IE_L3_350steps_1e8rate_03beta_cSFTDPO-gguf